© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 21828
    Prev
    Next
    INDEX
    Explanations

    Volkswagen and ITV

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on any token containing the letter sequence “vw” (in either upper‐ or lower‐case).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     \
    -3.44
    $
    -2.89
    that
    -2.75
    ↵
    -2.73
     flawless
    -2.73
     That
    -2.66
     n
    -2.42
     که
    -2.39
    较为
    -2.33
     r
    -2.19
    POSITIVE LOGITS
     Kontexten
    2.67
    妡
    2.66
     $_=
    2.58
     置物
    2.52
    媼
    2.47
    彇
    2.45
     墊
    2.44
    鱚
    2.41
    dámské
    2.38
    赑
    2.38
    Activations Density 0.002%

    No Known Activations